A comparison of constrained trajectory segment models for large vocabulary speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 6, Issue 3, 1998, Pages 303-306

  Kannan, Ashvin ^a   Ostendorf, Mari ^b  

^a NUANCE COMMUNICATIONS   (United States)

^b BOSTON UNIVERSITY   (United States)

Author keywords

Distribution clustering; Polynomial mean trajectory; Segment model

Indexed keywords

DESIGN; ESTIMATION; MATHEMATICAL MODELS; POLYNOMIALS;

CONSTRAINED TRAJECTORY SEGMENT MODELS;

SPEECH RECOGNITION;

EID: 0032069558     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.668825     Document Type: Article

References (19)

1. M. Ostendorf, V. V. Digalakis, and O. A. Kimball, "From HMM's to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 360-378, Sept. 1996.
2. O. Ghitza and M. Sondhi, "Hidden Markov models with templates as nonstationary states: An application to speech recognition," Comput. Speech Lang., vol. 2, pp. 101-119, 1993.
3. M. Ostendorf et al, "The 1994 NAB news benchmark system," in Proc. ARPA Spoken Language Technology Workshop, Jan. 1995, pp. 139-142'.
4. H. Gish and K. Ng, "A segmentai speech model with applications to word spotting," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1993, pp. 447-450.
5. L. Deng, M. Aksmanovic, X. Sun, and C. F. J. Wu, "Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states," IEEE Trans. Speech Audio Processing, vol. 2, pp. 507-520, Oct. 1994.
6. D. S. Pallett et al., "1994 benchmark tests for the ARPA spoken language program," in Proc. ARPA Spoken Lang. Technol. Workshop, Jan. 1995, pp. 5-36.
7. J. J. Godfrey, E. C. Holliman, and J. McDaniel, "Switchboard: Telephone speech corpus for research and development," in Proc. Int. Conf. Acoust., Speech, Signal Processing, vol. 1, pp. 517-520, 1992. .
8. A. Kannan, M. Ostendorf, and J. R. Rohlicek, "Maximum likelihood clustering of Gaussians for speech recognition," IEEE Trans. Speech Audio Processing, vol. 2, pp. 453-455, July 1994.
9. V. Digalakis, M. Ostendorf, and J. R. Rohlicek, "Improvements in the stochastic segment model for phoneme recognition," in Proc. DARPA Speech and Natural Language Workshop, 1989, pp. 332-338.
10. S. J. Young, J. J. Odell, and P. C. Woodland, 'Tree-based state tying for high accuracy acoustic modeling," in Proc. ARPA Workshop on Human Language Technology, 1994, pp. 307-312.
11. H. Gish and K. Ng, "Parametric trajectory models for speech recognition," in Proc. Int. Conf. Spoken Language Processing, vol. 1, pp. 466-469, Oct. 1996.
12. T. W. Anderson, An Introduction to Mullivariate Statistical Analysis, 2nd ed. New York: Wiley, 1984.
13. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, 1996, pp. 346-348.
14. L. Nguyen el al, "The 1994 BBN/BYBLOS speech recognition system," in Proc. ARPA Spoken Language Technology Workshop, Jan. 1995, pp. 77-81.
15. A. Kannan, M. Ostendorf, and J. R. Rohlicek, "Weight estimation for N-best rescoring," in Proc. DARPA Speech and Natural Language Workshop, Feb. 1992, pp. 455-456.
16. A. Kannan and M. Ostendorf, "Adaptation of polynomial trajectory segment models for large vocabulary speech recognition," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1997, vol. 2, pp. 1411-1414.
17. G. Zavaliagkos, R. Schwartz, J. McDonough, and J. Makhoul, "Adaptation algorithms for large scale HMM recognizers," in Proc. Europ. Conf. Speech Communications and Technology, 1995, pp. 1131-1134.
18. C. J. Leggetter and P. C. Woodland, "Speaker adaptation using maximum likelihood linear regression," Comput. Speech Lang., vol. 9, pp. 171-185, 1995.
19. W. J. Holmes and M. J. Russell, "Speech recognition using a linear dynamic segmental HMM," in Proc. Europ. Conf. Speech Communications and Technology, Sept. 1995, pp. 1611-1614.